We turn books people already trust into skills your agent can run.
Wondel.ai Skills is 50 frameworks from bestselling business and engineering books, packaged as free, MIT-licensed AI agent skills, plus 12 guided journeys that run them end to end. Everything is open source and installs in about 30 seconds.
What is Wondel.ai?
Wondel.ai is a product studio building consumer AI experiences. It is run by Wondel.ai sp. z o.o., based in Warsaw, and it publishes a number of products — wondel.ai is the studio's home.
Wondel.ai Skills is the studio's open-source library. It exists because the same problem kept recurring in our own work: an AI agent will write code, copy, or a strategy document confidently without applying any particular method, and the result is competent-looking output that a practitioner would immediately recognise as amateur. Handing the agent a specific, named framework fixes that — so we packaged 50 of them across 8 domains.
Who builds these skills?
A small team led by Michał Jaskólski, founder of Wondel.ai. Michał has built and sold two companies — Nokaut.pl (~$22M IPO) and Morizon.pl (~$20M M&A) — and shipped consumer products to over four million users a month as CPO of Grupa Morizon, now part of Ringier Axel Springer.
He writes the guides on this site under his own name, and the skills are developed in the open, so the work is checkable rather than merely claimed. If a skill misrepresents a book, the issue tracker is the fastest way to tell us.
How a book becomes a skill
Turning a 300-page book into a few thousand words an agent loads on demand is an editorial decision, not an extraction. Here is how we make it.
- 01
Pick books that describe a method, not a mood
A book earns a skill if it contains a procedure someone else can follow — Fowler's refactoring catalogue, Cialdini's principles, the Value Equation. Business books that are mostly anecdote make bad skills, because there is nothing for an agent to apply.
- 02
Extract the operational core
Each skill keeps the parts that change what an agent does — the heuristics, the decision rules, the order of operations — and drops the case studies. That is why a skill is a few thousand words and the book is a few hundred pages, and why the book is still worth reading.
- 03
Write it as instructions, not a summary
A summary tells you what the book said. A skill tells your agent what to do differently: which questions to ask, what to flag, which transformation to apply. Every skill ships with example prompts because the trigger matters as much as the content.
- 04
Say where it does not apply
Every skill page names the situations where a different skill fits better, and where the framework is genuinely contested — Clean Code and Software Design disagree about function length, and we say so rather than pretending the library is one coherent doctrine.
- 05
Keep it in the open
Every skill is MIT-licensed and readable at https://github.com/wondelai/skills. You can check whether we represented a book fairly, fork the ones you disagree with, and open an issue when we get something wrong.
Why is it free?
Every skill is MIT-licensed, published at github.com/wondelai/skills, and built on the open agentskills.io standard, so nothing here is locked to one vendor — the same folder works in Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw and Hermes Agent.
The library is not the business. We build custom skills, agents and MCP integrations for teams, and the open library is the portfolio: you can read every line of it before deciding whether we would be any good at yours. If that is useful to you, that is what we do for a living. If it is not, take the skills anyway.
Contact
- [email protected]
- Issues and pull requests on GitHub
- Michał Jaskólski on LinkedIn
- Wondel.ai sp. z o.o., Twarda 18, 00-105 Warszawa, Poland
Don’t guess your AI engineering level.
Measure it.
AI Developer Scorecard
How production-grade is your AI engineering?
Twenty-five questions across the practices that separate vibe-coding from production-grade engineering. Instant score, per-section breakdown, and a 30/60/90-day playbook.
Score 0–75 · 30/60/90-day playbook Score yourself For CTOs & foundersCTO Scorecard
Is your engineering team ready for AI at scale?
Twenty-five questions on how your org adopts AI — adoption, governance, automation, and ROI. See where you sit on the path from Reactive to Strategic Leader.
Score 0–75 · Reactive → Strategic Leader Score your orgWe build the skills you already use. Now we’ll build yours.
Sprints from $3K · shipped to production, or you don’t pay the final milestone.